Retrieval-Augmented Text-to-Audio Generation.
Yi YuanHaohe LiuXubo LiuQiushi HuangMark D. PlumbleyWenwu WangPublished in: ICASSP (2024)
Keyphrases
- information retrieval
- audio content
- text retrieval
- text graphics
- spoken documents
- cross media
- multimedia
- multimedia search
- text generation
- multimedia information
- document analysis
- document indexing
- cross media retrieval
- retrieval engine
- cross modal
- multimedia documents
- lifelog
- image database
- conceptual retrieval
- text to speech
- content and structure
- text collections
- image retrieval
- information retrieval systems
- text indexing
- relevance feedback
- multimedia information retrieval
- content based video retrieval
- semantic content
- text mining
- content based retrieval
- document retrieval
- textual descriptions
- audio visual content
- metadata
- information extraction
- query expansion
- test collection
- human language
- visual information
- handwritten documents
- free text
- structured documents
- news video
- document content
- multimedia databases
- text documents
- retrieval systems
- user comments
- document level
- video sequences
- natural language generation
- search engine